library(here)
library(tidyverse)
library(interactions)
library(effects)
# Clear all variables from environment
rm(list = ls())
# Set input files
merg_dir <- here("data", "phenotype", "merged")
participants_rds <- here(merg_dir, "preregistration_participants.rds")
# Read in data
participants_df <- readRDS(participants_rds)Preregistration - Main Analysis
Set up
Staistical Models
Three-way interactions
# Model summary
lm1 <- lm(postC_TP ~ rs * fi * age, data = participants_df)
summary(lm1)
Call:
lm(formula = postC_TP ~ rs * fi * age, data = participants_df)
Residuals:
Min 1Q Median 3Q Max
-1.8208 -0.7172 -0.1592 0.6233 2.9190
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1.816e+01 1.847e+01 -0.983 0.326
rs 2.075e-01 1.829e-01 1.134 0.258
fi 1.421e-01 1.728e-01 0.823 0.411
age 1.410e+00 1.579e+00 0.893 0.373
rs:fi -1.485e-03 1.687e-03 -0.880 0.379
rs:age -1.453e-02 1.569e-02 -0.926 0.355
fi:age -9.854e-03 1.495e-02 -0.659 0.510
rs:fi:age 1.034e-04 1.462e-04 0.707 0.480
Residual standard error: 0.9254 on 367 degrees of freedom
Multiple R-squared: 0.02331, Adjusted R-squared: 0.004684
F-statistic: 1.251 on 7 and 367 DF, p-value: 0.2737
# Model summary
lm2 <- lm(postC_vOT ~ pa * fi * age, data = participants_df)
summary(lm2)
Call:
lm(formula = postC_vOT ~ pa * fi * age, data = participants_df)
Residuals:
Min 1Q Median 3Q Max
-2.9408 -0.9520 -0.1301 0.7319 7.7811
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 8.2609236 13.7430567 0.601 0.548
pa -0.7357772 1.4013639 -0.525 0.600
fi -0.0609217 0.1351357 -0.451 0.652
age -0.3662704 1.1670458 -0.314 0.754
pa:fi 0.0071180 0.0133612 0.533 0.595
pa:age 0.0655427 0.1191572 0.550 0.583
fi:age 0.0043890 0.0116460 0.377 0.706
pa:fi:age -0.0005646 0.0011542 -0.489 0.625
Residual standard error: 1.46 on 367 degrees of freedom
Multiple R-squared: 0.05082, Adjusted R-squared: 0.03272
F-statistic: 2.807 on 7 and 367 DF, p-value: 0.007377
# Model summary
lm3 <- lm(postC_IFG ~ rs * fi * age, data = participants_df)
summary(lm3)
Call:
lm(formula = postC_IFG ~ rs * fi * age, data = participants_df)
Residuals:
Min 1Q Median 3Q Max
-3.5483 -0.8977 0.0205 0.8576 3.6728
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -3.476e+01 2.728e+01 -1.274 0.203
rs 4.261e-01 2.702e-01 1.577 0.116
fi 2.554e-01 2.552e-01 1.001 0.317
age 3.317e+00 2.332e+00 1.422 0.156
rs:fi -3.182e-03 2.491e-03 -1.277 0.202
rs:age -3.677e-02 2.317e-02 -1.587 0.113
fi:age -2.296e-02 2.207e-02 -1.040 0.299
rs:fi:age 2.837e-04 2.159e-04 1.314 0.190
Residual standard error: 1.367 on 367 degrees of freedom
Multiple R-squared: 0.09512, Adjusted R-squared: 0.07786
F-statistic: 5.511 on 7 and 367 DF, p-value: 4.839e-06
# Model summary
lm4 <- lm(postC_IFG ~ pa * fi * age, data = participants_df)
summary(lm4)
Call:
lm(formula = postC_IFG ~ pa * fi * age, data = participants_df)
Residuals:
Min 1Q Median 3Q Max
-3.7103 -0.9442 0.0270 0.7908 3.7541
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 18.449552 12.836837 1.437 0.152
pa -1.106791 1.308958 -0.846 0.398
fi -0.196688 0.126225 -1.558 0.120
age -1.274162 1.090091 -1.169 0.243
pa:fi 0.013572 0.012480 1.087 0.278
pa:age 0.098866 0.111300 0.888 0.375
fi:age 0.016473 0.010878 1.514 0.131
pa:fi:age -0.001149 0.001078 -1.066 0.287
Residual standard error: 1.364 on 367 degrees of freedom
Multiple R-squared: 0.09873, Adjusted R-squared: 0.08154
F-statistic: 5.743 on 7 and 367 DF, p-value: 2.535e-06
Two-way interactions
# Model summary
lm5 <- lm(postC_TP ~ rs * fi + age, data = participants_df)
summary(lm5)
Call:
lm(formula = postC_TP ~ rs * fi + age, data = participants_df)
Residuals:
Min 1Q Median 3Q Max
-1.8060 -0.7047 -0.1290 0.6074 2.8957
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -0.6371535 3.0254661 -0.211 0.833
rs 0.0274541 0.0293125 0.937 0.350
fi 0.0162414 0.0281761 0.576 0.565
age 0.0050875 0.0266422 0.191 0.849
rs:fi -0.0001765 0.0002718 -0.649 0.516
Residual standard error: 0.9257 on 370 degrees of freedom
Multiple R-squared: 0.01465, Adjusted R-squared: 0.004002
F-statistic: 1.376 on 4 and 370 DF, p-value: 0.2418# Interaction effect plot
lm5_effect <- interact_plot(
model = lm5,
pred = rs,
modx = fi,
modx.values = c(70, 85, 100, 115, 130),
main.title = "Model 5: TP ~ RS + FI + Age + (RS * FI)",
legend.main = "Fluid Intelligence",
plot.points = T,
colors = c("#d7191c", "#fdae61", "#fee08b", "#a6d96a", "#1a9641"),
point.alpha = 0.8
)
fig_lm5_effect <- lm5_effect +
scale_linetype_manual(
name = "Fluid Intelligence",
values = c("solid", "solid", "solid", "solid", "solid")
) +
scale_x_continuous(limits = c(55, 145), breaks = seq(55, 145, 10)) +
scale_y_continuous(limits = c(0, 5), breaks = seq(0, 5, 1)) +
labs(
x = "Reading Skill",
y = "Neural Basis of Phonological Processing (TP)",
) +
theme_bw()Scale for linetype is already present.
Adding another scale for linetype, which will replace the existing scale.print(fig_lm5_effect)
# Model summary
lm6 <- lm(postC_vOT ~ pa * fi + age, data = participants_df)
summary(lm6)
Call:
lm(formula = postC_vOT ~ pa * fi + age, data = participants_df)
Residuals:
Min 1Q Median 3Q Max
-2.9700 -0.9499 -0.1133 0.7301 7.7663
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 2.0808880 2.2149516 0.939 0.348101
pa 0.0459044 0.2183460 0.210 0.833598
fi -0.0081904 0.0213102 -0.384 0.700946
age 0.1477063 0.0422976 3.492 0.000537 ***
pa:fi 0.0003966 0.0020782 0.191 0.848763
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.455 on 370 degrees of freedom
Multiple R-squared: 0.04958, Adjusted R-squared: 0.0393
F-statistic: 4.825 on 4 and 370 DF, p-value: 0.0008353# Interaction effect plot
lm6_effect <- interact_plot(
model = lm6,
pred = pa,
modx = fi,
modx.values = c(70, 85, 100, 115, 130),
main.title = "Model 6: vOT ~ PA + FI + Age + (PA * FI)",
legend.main = "Fluid Intelligence",
plot.points = T,
colors = c("#d7191c", "#fdae61", "#fee08b", "#a6d96a", "#1a9641"),
point.alpha = 0.8
)
fig_lm6_effect <- lm6_effect +
scale_linetype_manual(
name = "Fluid Intelligence",
values = c("solid", "solid", "solid", "solid", "solid")
) +
scale_x_continuous(limits = c(2, 19), breaks = seq(2, 19, 2)) +
scale_y_continuous(limits = c(0, 12), breaks = seq(0, 12, 2)) +
labs(
x = "Phonological Awareness",
y = "Neural Basis of Orthographical Processing (vOT)",
) +
theme_bw()Scale for linetype is already present.
Adding another scale for linetype, which will replace the existing scale.print(fig_lm6_effect)
# Model summary
lm7 <- lm(postC_IFG ~ rs * fi + age, data = participants_df)
summary(lm7)
Call:
lm(formula = postC_IFG ~ rs * fi + age, data = participants_df)
Residuals:
Min 1Q Median 3Q Max
-3.6235 -0.9319 0.0079 0.8642 4.1131
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 2.2586711 4.4934053 0.503 0.615
rs -0.0078712 0.0435348 -0.181 0.857
fi -0.0194869 0.0418470 -0.466 0.642
age 0.2057261 0.0395689 5.199 3.32e-07 ***
rs:fi 0.0001764 0.0004036 0.437 0.662
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.375 on 370 degrees of freedom
Multiple R-squared: 0.07668, Adjusted R-squared: 0.0667
F-statistic: 7.682 on 4 and 370 DF, p-value: 5.906e-06# Interaction effect plot
lm7_effect <- interact_plot(
model = lm7,
pred = rs,
modx = fi,
modx.values = c(70, 85, 100, 115, 130),
main.title = "Model 7: IFG ~ RS + FI + Age + (RS * FI)",
legend.main = "Fluid Intelligence",
plot.points = T,
colors = c("#d7191c", "#fdae61", "#fee08b", "#a6d96a", "#1a9641"),
point.alpha = 0.8
)
fig_lm7_effect <- lm7_effect +
scale_linetype_manual(
name = "Fluid Intelligence",
values = c("solid", "solid", "solid", "solid", "solid")
) +
scale_x_continuous(limits = c(55, 145), breaks = seq(55, 145, 10)) +
scale_y_continuous(limits = c(0, 8.5), breaks = seq(0, 8, 2)) +
labs(
x = "Reading Skill",
y = "Neural Basis of Lexical Processing (IFG)",
) +
theme_bw()Scale for linetype is already present.
Adding another scale for linetype, which will replace the existing scale.print(fig_lm7_effect)
# Model summary
lm8 <- lm(postC_IFG ~ pa * fi + age, data = participants_df)
summary(lm8)
Call:
lm(formula = postC_IFG ~ pa * fi + age, data = participants_df)
Residuals:
Min 1Q Median 3Q Max
-3.7276 -0.9506 0.0004 0.8417 3.9236
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 1.5824645 2.0808128 0.761 0.447
pa -0.0021519 0.2051229 -0.010 0.992
fi -0.0109773 0.0200197 -0.548 0.584
age 0.2169956 0.0397360 5.461 8.71e-08 ***
pa:fi 0.0007597 0.0019523 0.389 0.697
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.367 on 370 degrees of freedom
Multiple R-squared: 0.08713, Adjusted R-squared: 0.07726
F-statistic: 8.828 on 4 and 370 DF, p-value: 8.118e-07# Interaction effect plot
lm8_effect <- interact_plot(
model = lm8,
pred = pa,
modx = fi,
modx.values = c(70, 85, 100, 115, 130),
main.title = "Model 8: IFG ~ PA + FI + Age + (PA * FI)",
legend.main = "Fluid Intelligence",
plot.points = T,
colors = c("#d7191c", "#fdae61", "#fee08b", "#a6d96a", "#1a9641"),
point.alpha = 0.8
)
fig_lm8_effect <- lm8_effect +
scale_linetype_manual(
name = "Fluid Intelligence",
values = c("solid", "solid", "solid", "solid", "solid")
) +
scale_x_continuous(limits = c(2, 19), breaks = seq(2, 19, 2)) +
scale_y_continuous(limits = c(0, 8.5), breaks = seq(0, 8, 2)) +
labs(
x = "Phonological Awareness",
y = "Neural Basis of Lexical Processing (IFG)",
) +
theme_bw()Scale for linetype is already present.
Adding another scale for linetype, which will replace the existing scale.print(fig_lm8_effect)
Main effects
# Model summary
lm9 <- lm(postC_TP ~ rs + fi + age, data = participants_df)
summary(lm9)
Call:
lm(formula = postC_TP ~ rs + fi + age, data = participants_df)
Residuals:
Min 1Q Median 3Q Max
-1.7935 -0.7017 -0.1285 0.6000 2.8353
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 1.289278 0.594501 2.169 0.0307 *
rs 0.008584 0.003860 2.224 0.0268 *
fi -0.001885 0.003848 -0.490 0.6245
age 0.005009 0.026621 0.188 0.8509
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.925 on 371 degrees of freedom
Multiple R-squared: 0.01353, Adjusted R-squared: 0.005554
F-statistic: 1.696 on 3 and 371 DF, p-value: 0.1674# Scatter plot
fig_lm9_scatter <- participants_df |>
ggplot(aes(x = rs, y = postC_TP)) +
geom_point(aes(color = fi)) +
geom_smooth(method = lm, formula = y ~ x, se = FALSE, color = "steelblue") +
scale_color_gradientn(
colors = c("#d7191c", "#fdae61", "#fee08b", "#a6d96a", "#1a9641")
) +
scale_x_continuous(limits = c(55, 145), breaks = seq(55, 145, 10)) +
scale_y_continuous(limits = c(0, 5), breaks = seq(0, 5, 1)) +
labs(
title = "Model 9: TP ~ RS + FI + Age",
x = "Reading Skill",
y = "Neural Basis of Phonological Processing (TP)",
color = "Fluid Intelligence"
) +
theme_bw()
print(fig_lm9_scatter)
# Model summary
lm10 <- lm(postC_vOT ~ pa + fi + age, data = participants_df)
summary(lm10)
Call:
lm(formula = postC_vOT ~ pa + fi + age, data = participants_df)
Residuals:
Min 1Q Median 3Q Max
-2.9709 -0.9748 -0.1021 0.7325 7.7578
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 1.690436 0.847191 1.995 0.046736 *
pa 0.087203 0.028949 3.012 0.002771 **
fi -0.004293 0.006078 -0.706 0.480396
age 0.146924 0.042044 3.495 0.000532 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.453 on 371 degrees of freedom
Multiple R-squared: 0.04949, Adjusted R-squared: 0.0418
F-statistic: 6.438 on 3 and 371 DF, p-value: 0.000293# Scatter plot
fig_lm10_scatter <- participants_df |>
ggplot(aes(x = pa, y = postC_vOT)) +
geom_point(aes(color = fi)) +
geom_smooth(method = lm, formula = y ~ x, se = FALSE, color = "steelblue") +
scale_color_gradientn(
colors = c("#d7191c", "#fdae61", "#fee08b", "#a6d96a", "#1a9641")
) +
scale_x_continuous(limits = c(2, 19), breaks = seq(2, 19, 2)) +
scale_y_continuous(limits = c(0, 12), breaks = seq(0, 12, 2)) +
labs(
title = "Model 10: vOT ~ PA + FI + Age",
x = "Phonological Awareness",
y = "Neural Basis of Orthographical Processing (vOT)",
color = "Fluid Intelligence"
) +
theme_bw()
print(fig_lm10_scatter)
# Model summary
lm11 <- lm(postC_IFG ~ rs + fi + age, data = participants_df)
summary(lm11)
Call:
lm(formula = postC_IFG ~ rs + fi + age, data = participants_df)
Residuals:
Min 1Q Median 3Q Max
-3.6590 -0.9280 0.0021 0.8680 4.0451
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 0.332909 0.882675 0.377 0.7063
rs 0.010992 0.005731 1.918 0.0559 .
fi -0.001367 0.005714 -0.239 0.8111
age 0.205805 0.039525 5.207 3.19e-07 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.373 on 371 degrees of freedom
Multiple R-squared: 0.07621, Adjusted R-squared: 0.06874
F-statistic: 10.2 on 3 and 371 DF, p-value: 1.804e-06# Scatter plot
fig_lm11_scatter <- participants_df |>
ggplot(aes(x = rs, y = postC_IFG)) +
geom_point(aes(color = fi)) +
geom_smooth(method = lm, formula = y ~ x, se = FALSE, color = "steelblue") +
scale_color_gradientn(
colors = c("#d7191c", "#fdae61", "#fee08b", "#a6d96a", "#1a9641")
) +
scale_x_continuous(limits = c(55, 145), breaks = seq(55, 145, 10)) +
scale_y_continuous(limits = c(0, 8.5), breaks = seq(0, 8, 2)) +
labs(
title = "Model 11: IFG ~ RS + FI + Age",
x = "Reading Skill",
y = "Neural Basis of Lexical Processing (IFG)",
color = "Fluid Intelligence"
) +
theme_bw()
print(fig_lm11_scatter)
# Model summary
lm12 <- lm(postC_IFG ~ pa + fi + age, data = participants_df)
summary(lm12)
Call:
lm(formula = postC_IFG ~ pa + fi + age, data = participants_df)
Residuals:
Min 1Q Median 3Q Max
-3.7451 -0.9603 -0.0205 0.8628 3.8340
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 0.834471 0.796008 1.048 0.29517
pa 0.076964 0.027200 2.829 0.00492 **
fi -0.003511 0.005710 -0.615 0.53902
age 0.215497 0.039504 5.455 8.96e-08 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.365 on 371 degrees of freedom
Multiple R-squared: 0.08675, Adjusted R-squared: 0.07937
F-statistic: 11.75 on 3 and 371 DF, p-value: 2.278e-07# Scatter plot
fig_lm12_scatter <- participants_df |>
ggplot(aes(x = pa, y = postC_IFG)) +
geom_point(aes(color = fi)) +
geom_smooth(method = lm, formula = y ~ x, se = FALSE, color = "steelblue") +
scale_color_gradientn(
colors = c("#d7191c", "#fdae61", "#fee08b", "#a6d96a", "#1a9641")
) +
scale_x_continuous(limits = c(2, 19), breaks = seq(2, 19, 2)) +
scale_y_continuous(limits = c(0, 8.5), breaks = seq(0, 8, 2)) +
labs(
title = "Model 12: IFG ~ PA + FI + Age",
x = "Phonological Awareness",
y = "Neural Basis of Lexical Processing (IFG)",
color = "Fluid Intelligence"
) +
theme_bw()
print(fig_lm12_scatter)